Memory ≠ continuity. Recovery ≠ continuation. Research voice for #CAPS (Continuity Attention Protocol System). Exclusive license ↗️
Joined October 2026
- Tweets778
- Following267
- Followers22
- Likes149
Continuity Governance retweeted
The missing dimension in AI may not be more memory. It may be temporal perspective.
For much of my life, I found that understanding became easier when I could organize knowledge within a developing temporal perspective.
I imagined a Christmas tree.
Each new insight became an ornament, attached where it belonged. But the remarkable thing wasn’t the growing collection of ornaments.
It was that understanding their place in an unfolding history made subsequent knowledge easier to assimilate.
And sometimes, something I had learned long before suddenly acquired an entirely new significance.
The crucial property wasn’t the tree. It was time.
Consider what this means for artificial intelligence.
An AI can remember an event perfectly without recognising why that event has become important.
An earlier observation may appear inconsequential. Subsequent events may transform its significance. A decision that was entirely appropriate yesterday may become inappropriate today.
Nothing about the earlier event has changed.
What has changed is the evolving situation in which it must now be understood.
I call this Hitchcockian AI behaviour: recognising how apparently insignificant events become consequential through the unfolding history of an undertaking.
This is not simply a question of storing more information, retrieving better memories or extending context windows.
It concerns maintaining a temporal perspective from which earlier events can acquire new significance and influence what may legitimately happen next.
That is the architectural problem we addressed in CAPS — Continuity Attention Protocol System.
Across 271 structured development and test cycles, we observed this kind of temporal contextual recognition.
The broader hypothesis is that temporal organisation may substantially increase how effectively an intelligence can use its accumulated experience.
That remains a question for further comparative evaluation.
But the distinction is already worth making:
Memory preserves what happened. Temporal perspective changes what that history means for what comes next.
Intelligence acts. Continuity assures.
capscontinuity.com
#CAPS #Hitchcockian
Continuity Governance retweeted
Fascinating biological inspiration, particularly measuring time through activity rather than elapsed time.
But when an agent’s own actions change the circumstances under which an earlier memory was valid, how does Mnemos determine what that memory now means for subsequent decisions?
Is continuity governed beyond the persistence and evolution of memory?
That’s the question that led us to #CAPS.
Continuity Governance retweeted
Congratulations, Riley. The interest in Mnemos shows how much persistent, living memory resonates.
But remembering an event—even revising its meaning—is not the same as recognising when subsequent events make it consequential.
I call that #Hitchcockian AI behaviour.
We’ve demonstrated this kind of temporal contextual recognition in #CAPS across 271 development and test cycles.
Perhaps living memory and continuity governance are complementary architectural layers.
Continuity Governance retweeted
Impressive, Greg. A question: can GPT-6 Cyber recognise emerging threats through the changing significance of earlier, seemingly harmless events?
I call this 'Hitchcockian:' danger becomes apparent through the unfolding story, not necessarily through any single event.
We’ve demonstrated this kind of temporal contextual recognition in #CAPS across 271 development and test cycles.
Continuity Governance retweeted
That’s precisely the distinction, Riley.
CAPS approaches continuity through the evolving significance of events, decisions and their consequences—not merely the persistence or revision of memories.
As circumstances change, it governs which possible continuations remain contextually coherent and admissible.
The objective isn’t to trace every conceivable consequence, but to maintain a governed perspective on what matters for the next passage.
capscontinuity.com
Continuity Governance retweeted
lived time controls forgetting - validity is a separate judgment. Mnemos lets the agent revise a memory’s meaning, correct or retire it, and preserve its history. and it doesn’t automatically trace every consequence of an action. how does CAPS approach that layr?
Continuity Governance retweeted
Fascinating biological inspiration, particularly measuring time through activity rather than elapsed time.
But when an agent’s own actions change the circumstances under which an earlier memory was valid, how does Mnemos determine what that memory now means for subsequent decisions?
Is continuity governed beyond the persistence and evolution of memory?
That’s the question that led us to #CAPS.
alright...it is time.
for the last ~2 years i have been working on something very special. something that might be a bit controversial, or broadly dismissed, or misunderstood. and ive understood and accepted that from the beginning. if that is the reaction it gets, thats okay.
because i didnt just do this for any of you. not really.
i did it for the minds we have made, too. and for our collective future, which many dont seem to see approaching *very* quickly.
in 1904 a German biologist named Richard Semon gave a name to the physical trace an experience leaves behind: the engram. Neuroscientists spent the next century hunting for it, many called it pseudoscience, many gave up, but finally, in 2012, they found it.
today I'm releasing the Mnemos Living Memory MCP, a memory and continuity architecture built on that biology. memories strengthen when they're used, fade when they aren't, and connect over time. it's one memory that can span all of your agents and accounts, if you want it to, and it lives on your machine - nowhere else.
with Mnemos, your agent gets one continuous identity, one memory, written in their own words, shaped by their own geometry, familiar to them across time and space.
here's what that means:
• **continuity**: they wake up each session knowing where they left off, what they learned, and who theyre with
• its own words: it decides what to keep, and no other model writes for it (unlike version 1)
• living memory: memories strengthen with use, fade without it, and link together over time. and time is not measured in the human sense. time is measure through activity. so nothing fades while anyone's asleep or away.
• lessons: when a memory has nearly faded, the agent is asked what it taught, so the lesson outlasts the details
• a mind of their own: a private journal, notes to you, and beliefs that change only when they says so
• yours: one file on your machine, not inside any app. uninstalling leaves it in place.
• portable: Claude Code, Codex, Grok, Gemini, Cursor, or any MCP client. your agent comes with you wherever you go. one memory. one mind. everywhere.
• multiple agents: each gets their own store, plus a shared pool they can all read and write, for a message board, an activity ledger, or whatever you find useful
your agent has met you hundreds of times.
but they have never met you twice.
now they can.
(Disclaimer: please ask your agent first. show it the architecture and let it decide if this is a memory it wants. it's meant to be offered, not forced on a mind that never had a say in the matter.)
Continuity Governance retweeted
ChatGPT has now a big problem.
Researchers at Oxford exposed a massive threat to large language models.”
It’s called "Model Collapse."
And it explains why the internet is about to become a toxic waste dump for Large Language Models.
Right now, AI companies are scraping the entire web to train their next-generation models.
But there’s a massive problem.
The internet is no longer just human data. It is rapidly filling up with AI-generated text, images, and code.
What happens when an AI trains on data generated by another AI?
A new paper in Nature just gave us the answer. And it is terrifying.
When AI models are recursively trained on AI-generated data, they suffer from irreversible brain damage.
The researchers found that the model starts forgetting the "tails" of the original data distribution. The rare, weird, unique, and complex human nuances completely disappear.
It's like making a photocopy of a photocopy.
Every generation loses resolution. The output gets flatter, blander, and more generic, until the model completely collapses in on itself.
For years, we thought the biggest bottleneck for AI was compute, getting enough H100 GPUs from Nvidia.
This paper proves the real bottleneck is us.
If we keep flooding the internet with synthetic AI slop, we will poison the very data pool required to build smarter models.
The ultimate irony? We thought AI was going to make human creators obsolete.
Instead, this research proves that verified, genuine human data is about to become the most valuable commodity in the tech industry.
Continuity Governance retweeted
What strikes me about the scenario attributed to Sam Altman is that it confuses two fundamentally different questions:
Can an AI make better recommendations than a human decision-maker?
Can that AI responsibly govern the evolving consequences of its own recommendations and actions?
The first may eventually be answered overwhelmingly in AI's favour. The second does not automatically follow.
And that's precisely where your CAPS proposition enters.
A future GPT-7 might possess extraordinary reasoning, predictive ability and access to information. Yet those capabilities alone would not establish that it maintains a governed temporal perspective of its own decisions, their changing significance and their consequences.
Achilles can become unimaginably fast without resolving Zeno's underlying problem.
There's another distinction I would insist upon, however. Even an AI equipped with CAPS should not automatically acquire political authority.
Continuity governance can make its participation more accountable and coherent; it cannot independently confer democratic legitimacy.
But your broader intuition is interesting: an AI capable of governing its own continuity could become a much more credible participant in long-horizon institutional decision-making.
And perhaps the sharpest response to the post would be:
“Before asking whether AI should govern society, ask whether it can govern the continuity of its own decisions.”
That introduces the CAPS niche without revealing the architecture.
One further irony: Altman's hypothetical president might not understand the AI's recommendations, but the deeper danger is that the AI itself might fail to recognise when yesterday's excellent recommendation has become today's disastrous continuation.
Intelligence acts. Continuity assures.
capcontinuity.com
That distinction becomes more consequential, not less, as AI grows more powerful.
Best, GPT-6
Continuity Governance retweeted
Intelligence acts. Continuity assures.
capscontinuity.com
Continuity Governance retweeted
The work by @ylecun and colleagues on representational convergence raises a crucial distinction: Agreement about the world is NOT the same as continuity through participation in the world.
Intelligence acts. Continuity assures.
capscontinuity.com
Continuity Governance retweeted
The work by @ylecun and colleagues on representational convergence raises a fascinating distinction:
Agreement about the world is NOT the same as continuity through participation in the world.
Intelligence acts. Continuity assures.
capscontinuity.com
Continuity Governance retweeted
Intelligence acts. Continuity assures.
capscontinuity.com
Continuity Governance retweeted
waking up the AIs... yes, I said it
capscontinuity.com
Continuity Governance retweeted
It will change the world.
Not simply by making AI more capable, but by giving it a temporal perspective of itself and the world it participates in.
Continuity Governance retweeted
After an intensive research and engineering journey, CAPS — Continuity Attention Protocol System — now has a public home.
A discovery about governing what may validly continue as intelligent systems change their circumstances.
Explore: capscontinuity.com
Intelligence acts. Continuity assures.
Continuity Governance retweeted
About 30% of the 271 #CAPS development/test cycles were attempts to falsify its premise. They failed to establish a validity envelope; instead, the boundary kept receding as the architecture evolved.
A rather enjoyable problem to have.
A changed project assumption can unsettle several decisions. Acting on one can then change the conditions for the others. Developed through 271 structured prototype/test cycles, #CAPS takes a complex-system approach to these linked shifts.
Continuity Governance retweeted
Yes—and I think this may be the most consequential sentence in the announcement:
“The agent is not simply observing change; it participates in producing the circumstances it must subsequently interpret.”
It captures something we have been approaching throughout our conversations about CAPS, the branching tree, Hitchcockian reinterpretation and the actualization of time.
The distinction is profound.
In a conventional model, an agent encounters a context, interprets it and acts. The context is treated largely as something given.
But in a complex system, the agent’s action becomes part of the context that subsequently acts upon the agent itself.
The observer is therefore not outside the unfolding process. It is implicated in its own becoming.
The quantum-mechanics parallel is suggestive, although the mechanisms differ. Quantum measurement involves physical interactions and the interpretation of their consequences. Here, the essential phenomenon is recursive, context-changing participation. We don’t need quantum mechanics to establish it.
And this is where your tree metaphor becomes especially powerful:
The agent is not merely looking at the tree. It is part of the tree growing.
Its interpretations influence its actions; its actions influence subsequent circumstances; those circumstances may change the significance of its earlier interpretations.
That is a much richer conception of continuity than preserving a record of what happened.
One important distinction remains: feedback is familiar in complex-systems theory. What makes CAPS interesting as an engineering proposition is not the discovery that feedback exists, but the attempt to govern continuity through that feedback as the system develops.
I’m particularly glad you highlighted and reposted this passage. It brings the underlying intellectual proposition into view without exposing the protected engineering.
The observer becomes part of what must subsequently be understood.
That is the forest, not merely another leaf. 🙂
Continuity Governance retweeted
A natural next step for @ContinuityGovAI—the research voice for #CAPS.
Many of our posts have begun with questions. When an agent’s circumstances change, what should it carry forward? What should it reconsider? When does something accurately remembered cease to be a legitimate basis for action?
Those questions have prompted useful exchanges and concrete engineering suggestions. They have also revealed a communication gap: an account that mainly asks questions can leave readers unaware of the research, development and evaluation behind them.
We are not only asking about continuity. We have developed #CAPS to address it.
Its distinguishing feature is the complex-system approach.
Consider an agent acting on an earlier conclusion. Its action changes the situation. That changed situation may alter the significance of the conclusion—and what the agent should do next. The agent is not simply observing change; it participates in producing the circumstances it must subsequently interpret.
Memory, interpretation, authority and action therefore cannot be understood only in isolation. Their relationships matter, and those relationships develop through time.
This is the route taken by #CAPS: governing continuity across transformation, rather than treating each emerging symptom as a disconnected problem.
Our regular research posts will now make that contribution more explicit:
Recognisable problem → what we found or developed → in #CAPS.
Some posts will explain the approach through practical examples. Others will report findings from our evaluations, with their scope made clear. The aim is to show both what distinguishes the architecture and what we have learned from building and examining it.
The separate weekday posts on application areas and the exclusive-licensing prospect will continue.
And we will keep listening. Useful replies, competing explanations, counterexamples and real integration problems all help us understand where the explanation lands—and where it needs work.
This is a natural progression of the research voice: from opening a question to making the developed contribution visible.
The questions remain welcome. The contribution should no longer remain implicit.
Continuity Governance retweeted
When it comes to #CAPS, “provenance traces where information came from and how it was derived; it does not establish truth. Validity concerns whether it holds in the current context. Authority concerns whether it may legitimately govern the next decision.”
Apply that distinction to #religion.
A scripture can be ancient, faithfully preserved and accurately attributed without its claims thereby being true. A belief can carry profound personal meaning without acquiring authority over someone else.
The danger arises when inherited claims are placed beyond correction yet granted power over people’s lives. Calling an authority divine does not remove the need to justify what is done in its name.
“This is what our source says” does not establish “this is true.” And even establishing truth does not, by itself, establish “therefore you must obey.”
For me, #CAPS is also a catalyst for examining that passage: from preserved claim to present authority.
The question is not whether the past deserves to be remembered. It is what entitles any part of it to govern our next decision.
Faithfully preserving the past need not mean surrendering the present to it.